rulebasedcollator.java

java源代码 请看看啊 提点宝贵的意见

                                                // (strength is TERTIARY)
                                checkTertiary = false;
                            }
                        }
                    }
                } // if (checkSecTer)

            }  // if ( pSOrder != pTOrder )
        } // while()

        if (sOrder != CollationElementIterator.NULLORDER) {
            // (tOrder must be CollationElementIterator::NULLORDER,
            //  since this point is only reached when sOrder or tOrder is NULLORDER.)
            // The source string has more elements, but the target string hasn't.
            do {
                if (CollationElementIterator.primaryOrder(sOrder) != 0) {
                    // We found an additional non-ignorable base character in the source string.
                    // This is a primary difference, so the source is greater
                    return Collator.GREATER; // (strength is PRIMARY)
                }
                else if (CollationElementIterator.secondaryOrder(sOrder) != 0) {
                    // Additional secondary elements mean the source string is greater
                    if (checkSecTer) {
                        result = Collator.GREATER;  // (strength is SECONDARY)
                        checkSecTer = false;
                    }
                }
            } while ((sOrder = sourceCursor.next()) != CollationElementIterator.NULLORDER);
        }
        else if (tOrder != CollationElementIterator.NULLORDER) {
            // The target string has more elements, but the source string hasn't.
            do {
                if (CollationElementIterator.primaryOrder(tOrder) != 0)
                    // We found an additional non-ignorable base character in the target string.
                    // This is a primary difference, so the source is less
                    return Collator.LESS; // (strength is PRIMARY)
                else if (CollationElementIterator.secondaryOrder(tOrder) != 0) {
                    // Additional secondary elements in the target mean the source string is less
                    if (checkSecTer) {
                        result = Collator.LESS;  // (strength is SECONDARY)
                        checkSecTer = false;
                    }
                }
            } while ((tOrder = targetCursor.next()) != CollationElementIterator.NULLORDER);
        }

        // For IDENTICAL comparisons, we use a bitwise character comparison
        // as a tiebreaker if all else is equal
        if (result == 0 && getStrength() == IDENTICAL) {
            Normalizer.Mode mode = NormalizerUtilities.toNormalizerMode(getDecomposition());
            String sourceDecomposition = Normalizer.normalize(source, mode, 0);
            String targetDecomposition = Normalizer.normalize(target, mode, 0);
            result = sourceDecomposition.compareTo(targetDecomposition);
        }
        return result;
    }

    /**
     * Transforms the string into a series of characters that can be compared
     * with CollationKey.compareTo. This overrides java.text.Collator.getCollationKey.
     * It can be overriden in a subclass.
     */
    public synchronized CollationKey getCollationKey(String source)
    {
        //
        // The basic algorithm here is to find all of the collation elements for each
        // character in the source string, convert them to a char representation,
        // and put them into the collation key.  But it's trickier than that.
        // Each collation element in a string has three components: primary (A vs B),
        // secondary (A vs A-acute), and tertiary (A' vs a); and a primary difference
        // at the end of a string takes precedence over a secondary or tertiary
        // difference earlier in the string.
        //
        // To account for this, we put all of the primary orders at the beginning of the
        // string, followed by the secondary and tertiary orders, separated by nulls.
        //
        // Here's a hypothetical example, with the collation element represented as
        // a three-digit number, one digit for primary, one for secondary, etc.
        //
        // String:              A     a     B   \u00e9 <--(e-acute)
        // Collation Elements: 101   100   201  510
        //
        // Collation Key:      1125<null>0001<null>1010
        //
        // To make things even trickier, secondary differences (accent marks) are compared
        // starting at the *end* of the string in languages with French secondary ordering.
        // But when comparing the accent marks on a single base character, they are compared
        // from the beginning.  To handle this, we reverse all of the accents that belong
        // to each base character, then we reverse the entire string of secondary orderings
        // at the end.  Taking the same example above, a French collator might return
        // this instead:
        //
        // Collation Key:      1125<null>1000<null>1010
        //
        if (source == null)
            return null;

        if (primResult == null) {
            primResult = new StringBuffer();
            secResult = new StringBuffer();
            terResult = new StringBuffer();
        } else {
            primResult.setLength(0);
            secResult.setLength(0);
            terResult.setLength(0);
        }
        int order = 0;
        boolean compareSec = (getStrength() >= Collator.SECONDARY);
        boolean compareTer = (getStrength() >= Collator.TERTIARY);
        int secOrder = CollationElementIterator.NULLORDER;
        int terOrder = CollationElementIterator.NULLORDER;
        int preSecIgnore = 0;

        if (sourceCursor == null) {
            sourceCursor = getCollationElementIterator(source);
        } else {
            sourceCursor.setText(source);
        }

        // walk through each character
        while ((order = sourceCursor.next()) !=
               CollationElementIterator.NULLORDER)
        {
            secOrder = CollationElementIterator.secondaryOrder(order);
            terOrder = CollationElementIterator.tertiaryOrder(order);
            if (!CollationElementIterator.isIgnorable(order))
            {
                primResult.append((char) (CollationElementIterator.primaryOrder(order)
                                    + COLLATIONKEYOFFSET));

                if (compareSec) {
                    //
                    // accumulate all of the ignorable/secondary characters attached
                    // to a given base character
                    //
                    if (tables.isFrenchSec() && preSecIgnore < secResult.length()) {
                        //
                        // We're doing reversed secondary ordering and we've hit a base
                        // (non-ignorable) character.  Reverse any secondary orderings
                        // that applied to the last base character.  (see block comment above.)
                        //
                        RBCollationTables.reverse(secResult, preSecIgnore, secResult.length());
                    }
                    // Remember where we are in the secondary orderings - this is how far
                    // back to go if we need to reverse them later.
                    secResult.append((char)(secOrder+ COLLATIONKEYOFFSET));
                    preSecIgnore = secResult.length();
                }
                if (compareTer) {
                    terResult.append((char)(terOrder+ COLLATIONKEYOFFSET));
                }
            }
            else
            {
                if (compareSec && secOrder != 0)
                    secResult.append((char)
                        (secOrder + tables.getMaxSecOrder() + COLLATIONKEYOFFSET));
                if (compareTer && terOrder != 0)
                    terResult.append((char)
                        (terOrder + tables.getMaxTerOrder() + COLLATIONKEYOFFSET));
            }
        }
        if (tables.isFrenchSec())
        {
            if (preSecIgnore < secResult.length()) {
                // If we've accumlated any secondary characters after the last base character,
                // reverse them.
                RBCollationTables.reverse(secResult, preSecIgnore, secResult.length());
            }
            // And now reverse the entire secResult to get French secondary ordering.
            RBCollationTables.reverse(secResult, 0, secResult.length());
        }
        primResult.append((char)0);
        secResult.append((char)0);
        secResult.append(terResult.toString());
        primResult.append(secResult.toString());

        if (getStrength() == IDENTICAL) {
            primResult.append((char)0);
            Normalizer.Mode mode = NormalizerUtilities.toNormalizerMode(getDecomposition());
            primResult.append(Normalizer.normalize(source, mode, 0));
        }
        return new CollationKey(source, primResult.toString());
    }

    /**
     * Standard override; no change in semantics.
     */
    public Object clone() {
        // if we know we're not actually a subclass of RuleBasedCollator
        // (this class really should have been made final), bypass
        // Object.clone() and use our "copy constructor".  This is faster.
        if (getClass() == RuleBasedCollator.class) {
            return new RuleBasedCollator(this);
        }
        else {
            RuleBasedCollator result = (RuleBasedCollator) super.clone();
            result.primResult = null;
            result.secResult = null;
            result.terResult = null;
            result.sourceCursor = null;
            result.targetCursor = null;
            return result;
        }
    }

    /**
     * Compares the equality of two collation objects.
     * @param obj the table-based collation object to be compared with this.
     * @return true if the current table-based collation object is the same
     * as the table-based collation object obj; false otherwise.
     */
    public boolean equals(Object obj) {
        if (obj == null) return false;
        if (!super.equals(obj)) return false;  // super does class check
        RuleBasedCollator other = (RuleBasedCollator) obj;
        // all other non-transient information is also contained in rules.
        return (getRules().equals(other.getRules()));
    }

    /**
     * Generates the hash code for the table-based collation object
     */
    public int hashCode() {
        return getRules().hashCode();
    }

    /**
     * Allows CollationElementIterator access to the tables object
     */
    RBCollationTables getTables() {
        return tables;
    }

    // ==============================================================
    // private
    // ==============================================================

    final static int CHARINDEX = 0x70000000;  // need look up in .commit()
    final static int EXPANDCHARINDEX = 0x7E000000; // Expand index follows
    final static int CONTRACTCHARINDEX = 0x7F000000;  // contract indexes follow
    final static int UNMAPPED = 0xFFFFFFFF;

    private final static int COLLATIONKEYOFFSET = 1;

    private RBCollationTables tables = null;

    // Internal objects that are cached across calls so that they don't have to
    // be created/destroyed on every call to compare() and getCollationKey()
    private StringBuffer primResult = null;
    private StringBuffer secResult = null;
    private StringBuffer terResult = null;
    private CollationElementIterator sourceCursor = null;
    private CollationElementIterator targetCursor = null;
}